Skip to content

Q
qemu

openeuler / qemu

通知 10
Star 0
Fork 0
Q
qemu
提交 5281d757 编写于 作者: M Mark McLoughlin 提交者： Anthony Liguori
浏览文件
操作

net: split all the tap code out into net/tap.c 

Signed-off-by: NMark McLoughlin <markmc@redhat.com>
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>
上级 f54c7bdc
展开全部 隐藏空白更改
内联 并排
Showing with 763 addition and 691 deletion
Makefile
浏览文件 @ 5281d757
......@@ -88,6 +88,7 @@ block-obj-y += $(addprefix block/, $(block-nested-y))
net-obj-y = net.o
net-nested-y = queue.o checksum.o
net-nested-$(CONFIG_POSIX) += tap.o
net-nested-$(CONFIG_WIN32) += tap-win32.o
net-obj-y += $(addprefix net/, $(net-nested-y))
......
net.c
浏览文件 @ 5281d757
......@@ -42,12 +42,6 @@
#include <sys/socket.h>
#include <netinet/in.h>
#include <net/if.h>
#ifdef __NetBSD__
#include <net/if_tap.h>
#endif
#ifdef __linux__
#include "net/tap-linux.h"
#endif
#include <arpa/inet.h>
#include <dirent.h>
#include <netdb.h>
......@@ -1295,618 +1289,6 @@ void do_info_usernet(Monitor *mon)
#endif /* CONFIG_SLIRP */
#if !defined(_WIN32) && !defined(_AIX)
/* Maximum GSO packet size (64k) plus plenty of room for
* the ethernet and virtio_net headers
*/
#define TAP_BUFSIZE (4096 + 65536)
typedef struct TAPState {
VLANClientState *vc;
int fd;
char down_script[1024];
char down_script_arg[128];
uint8_t buf[TAP_BUFSIZE];
unsigned int read_poll : 1;
unsigned int write_poll : 1;
unsigned int has_vnet_hdr : 1;
unsigned int using_vnet_hdr : 1;
unsigned int has_ufo: 1;
} TAPState;
static int launch_script(const char *setup_script, const char *ifname, int fd);
static int tap_can_send(void *opaque);
static void tap_send(void *opaque);
static void tap_writable(void *opaque);
static void tap_update_fd_handler(TAPState *s)
{
qemu_set_fd_handler2(s->fd,
s->read_poll ? tap_can_send : NULL,
s->read_poll ? tap_send : NULL,
s->write_poll ? tap_writable : NULL,
s);
}
static void tap_read_poll(TAPState *s, int enable)
{
s->read_poll = !!enable;
tap_update_fd_handler(s);
}
static void tap_write_poll(TAPState *s, int enable)
{
s->write_poll = !!enable;
tap_update_fd_handler(s);
}
static void tap_writable(void *opaque)
{
TAPState *s = opaque;
tap_write_poll(s, 0);
qemu_flush_queued_packets(s->vc);
}
static ssize_t tap_write_packet(TAPState *s, const struct iovec *iov, int iovcnt)
{
ssize_t len;
do {
len = writev(s->fd, iov, iovcnt);
} while (len == -1 && errno == EINTR);
if (len == -1 && errno == EAGAIN) {
tap_write_poll(s, 1);
return 0;
}
return len;
}
static ssize_t tap_receive_iov(VLANClientState *vc, const struct iovec *iov,
int iovcnt)
{
TAPState *s = vc->opaque;
const struct iovec *iovp = iov;
struct iovec iov_copy[iovcnt + 1];
struct virtio_net_hdr hdr = { 0, };
if (s->has_vnet_hdr && !s->using_vnet_hdr) {
iov_copy[0].iov_base = &hdr;
iov_copy[0].iov_len = sizeof(hdr);
memcpy(&iov_copy[1], iov, iovcnt * sizeof(*iov));
iovp = iov_copy;
iovcnt++;
}
return tap_write_packet(s, iovp, iovcnt);
}
static ssize_t tap_receive_raw(VLANClientState *vc, const uint8_t *buf, size_t size)
{
TAPState *s = vc->opaque;
struct iovec iov[2];
int iovcnt = 0;
struct virtio_net_hdr hdr = { 0, };
if (s->has_vnet_hdr) {
iov[iovcnt].iov_base = &hdr;
iov[iovcnt].iov_len = sizeof(hdr);
iovcnt++;
}
iov[iovcnt].iov_base = (char *)buf;
iov[iovcnt].iov_len = size;
iovcnt++;
return tap_write_packet(s, iov, iovcnt);
}
static ssize_t tap_receive(VLANClientState *vc, const uint8_t *buf, size_t size)
{
TAPState *s = vc->opaque;
struct iovec iov[1];
if (s->has_vnet_hdr && !s->using_vnet_hdr) {
return tap_receive_raw(vc, buf, size);
}
iov[0].iov_base = (char *)buf;
iov[0].iov_len = size;
return tap_write_packet(s, iov, 1);
}
static int tap_can_send(void *opaque)
{
TAPState *s = opaque;
return qemu_can_send_packet(s->vc);
}
#ifdef __sun__
static ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen)
{
struct strbuf sbuf;
int f = 0;
sbuf.maxlen = maxlen;
sbuf.buf = (char *)buf;
return getmsg(tapfd, NULL, &sbuf, &f) >= 0 ? sbuf.len : -1;
}
#else
static ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen)
{
return read(tapfd, buf, maxlen);
}
#endif
static void tap_send_completed(VLANClientState *vc, ssize_t len)
{
TAPState *s = vc->opaque;
tap_read_poll(s, 1);
}
static void tap_send(void *opaque)
{
TAPState *s = opaque;
int size;
do {
uint8_t *buf = s->buf;
size = tap_read_packet(s->fd, s->buf, sizeof(s->buf));
if (size <= 0) {
break;
}
if (s->has_vnet_hdr && !s->using_vnet_hdr) {
buf += sizeof(struct virtio_net_hdr);
size -= sizeof(struct virtio_net_hdr);
}
size = qemu_send_packet_async(s->vc, buf, size, tap_send_completed);
if (size == 0) {
tap_read_poll(s, 0);
}
} while (size > 0);
}
/* sndbuf should be set to a value lower than the tx queue
* capacity of any destination network interface.
* Ethernet NICs generally have txqueuelen=1000, so 1Mb is
* a good default, given a 1500 byte MTU.
*/
#define TAP_DEFAULT_SNDBUF 1024*1024
static int tap_set_sndbuf(TAPState *s, QemuOpts *opts)
{
int sndbuf;
sndbuf = qemu_opt_get_size(opts, "sndbuf", TAP_DEFAULT_SNDBUF);
if (!sndbuf) {
sndbuf = INT_MAX;
}
if (ioctl(s->fd, TUNSETSNDBUF, &sndbuf) == -1 && qemu_opt_get(opts, "sndbuf")) {
qemu_error("TUNSETSNDBUF ioctl failed: %s\n", strerror(errno));
return -1;
}
return 0;
}
int tap_has_ufo(VLANClientState *vc)
{
TAPState *s = vc->opaque;
assert(vc->type == NET_CLIENT_TYPE_TAP);
return s->has_ufo;
}
int tap_has_vnet_hdr(VLANClientState *vc)
{
TAPState *s = vc->opaque;
assert(vc->type == NET_CLIENT_TYPE_TAP);
return s->has_vnet_hdr;
}
void tap_using_vnet_hdr(VLANClientState *vc, int using_vnet_hdr)
{
TAPState *s = vc->opaque;
using_vnet_hdr = using_vnet_hdr != 0;
assert(vc->type == NET_CLIENT_TYPE_TAP);
assert(s->has_vnet_hdr == using_vnet_hdr);
s->using_vnet_hdr = using_vnet_hdr;
}
static int tap_probe_vnet_hdr(int fd)
{
struct ifreq ifr;
if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
qemu_error("TUNGETIFF ioctl() failed: %s\n", strerror(errno));
return 0;
}
return ifr.ifr_flags & IFF_VNET_HDR;
}
void tap_set_offload(VLANClientState *vc, int csum, int tso4,
int tso6, int ecn, int ufo)
{
TAPState *s = vc->opaque;
unsigned int offload = 0;
if (csum) {
offload |= TUN_F_CSUM;
if (tso4)
offload |= TUN_F_TSO4;
if (tso6)
offload |= TUN_F_TSO6;
if ((tso4 || tso6) && ecn)
offload |= TUN_F_TSO_ECN;
if (ufo)
offload |= TUN_F_UFO;
}
if (ioctl(s->fd, TUNSETOFFLOAD, offload) != 0) {
offload &= ~TUN_F_UFO;
if (ioctl(s->fd, TUNSETOFFLOAD, offload) != 0) {
fprintf(stderr, "TUNSETOFFLOAD ioctl() failed: %s\n",
strerror(errno));
}
}
}
static void tap_cleanup(VLANClientState *vc)
{
TAPState *s = vc->opaque;
qemu_purge_queued_packets(vc);
if (s->down_script[0])
launch_script(s->down_script, s->down_script_arg, s->fd);
tap_read_poll(s, 0);
tap_write_poll(s, 0);
close(s->fd);
qemu_free(s);
}
/* fd support */
static TAPState *net_tap_fd_init(VLANState *vlan,
const char *model,
const char *name,
int fd,
int vnet_hdr)
{
TAPState *s;
unsigned int offload;
s = qemu_mallocz(sizeof(TAPState));
s->fd = fd;
s->has_vnet_hdr = vnet_hdr != 0;
s->using_vnet_hdr = 0;
s->vc = qemu_new_vlan_client(NET_CLIENT_TYPE_TAP,
vlan, NULL, model, name, NULL,
tap_receive, tap_receive_raw,
tap_receive_iov, tap_cleanup, s);
s->has_ufo = 0;
/* Check if tap supports UFO */
offload = TUN_F_CSUM | TUN_F_UFO;
if (ioctl(s->fd, TUNSETOFFLOAD, offload) == 0)
s->has_ufo = 1;
tap_set_offload(s->vc, 0, 0, 0, 0, 0);
tap_read_poll(s, 1);
return s;
}
#if defined (CONFIG_BSD) || defined (__FreeBSD_kernel__)
static int tap_open(char *ifname, int ifname_size,
int *vnet_hdr, int vnet_hdr_required)
{
int fd;
char *dev;
struct stat s;
TFR(fd = open("/dev/tap", O_RDWR));
if (fd < 0) {
fprintf(stderr, "warning: could not open /dev/tap: no virtual network emulation\n");
return -1;
}
fstat(fd, &s);
dev = devname(s.st_rdev, S_IFCHR);
pstrcpy(ifname, ifname_size, dev);
fcntl(fd, F_SETFL, O_NONBLOCK);
return fd;
}
#elif defined(__sun__)
#define TUNNEWPPA (('T'<<16) | 0x0001)
/*
* Allocate TAP device, returns opened fd.
* Stores dev name in the first arg(must be large enough).
*/
static int tap_alloc(char *dev, size_t dev_size)
{
int tap_fd, if_fd, ppa = -1;
static int ip_fd = 0;
char *ptr;
static int arp_fd = 0;
int ip_muxid, arp_muxid;
struct strioctl strioc_if, strioc_ppa;
int link_type = I_PLINK;;
struct lifreq ifr;
char actual_name[32] = "";
memset(&ifr, 0x0, sizeof(ifr));
if( *dev ){
ptr = dev;
while( *ptr && !qemu_isdigit((int)*ptr) ) ptr++;
ppa = atoi(ptr);
}
/* Check if IP device was opened */
if( ip_fd )
close(ip_fd);
TFR(ip_fd = open("/dev/udp", O_RDWR, 0));
if (ip_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/ip (actually /dev/udp)");
return -1;
}
TFR(tap_fd = open("/dev/tap", O_RDWR, 0));
if (tap_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/tap");
return -1;
}
/* Assign a new PPA and get its unit number. */
strioc_ppa.ic_cmd = TUNNEWPPA;
strioc_ppa.ic_timout = 0;
strioc_ppa.ic_len = sizeof(ppa);
strioc_ppa.ic_dp = (char *)&ppa;
if ((ppa = ioctl (tap_fd, I_STR, &strioc_ppa)) < 0)
syslog (LOG_ERR, "Can't assign new interface");
TFR(if_fd = open("/dev/tap", O_RDWR, 0));
if (if_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/tap (2)");
return -1;
}
if(ioctl(if_fd, I_PUSH, "ip") < 0){
syslog(LOG_ERR, "Can't push IP module");
return -1;
}
if (ioctl(if_fd, SIOCGLIFFLAGS, &ifr) < 0)
syslog(LOG_ERR, "Can't get flags\n");
snprintf (actual_name, 32, "tap%d", ppa);
pstrcpy(ifr.lifr_name, sizeof(ifr.lifr_name), actual_name);
ifr.lifr_ppa = ppa;
/* Assign ppa according to the unit number returned by tun device */
if (ioctl (if_fd, SIOCSLIFNAME, &ifr) < 0)
syslog (LOG_ERR, "Can't set PPA %d", ppa);
if (ioctl(if_fd, SIOCGLIFFLAGS, &ifr) <0)
syslog (LOG_ERR, "Can't get flags\n");
/* Push arp module to if_fd */
if (ioctl (if_fd, I_PUSH, "arp") < 0)
syslog (LOG_ERR, "Can't push ARP module (2)");
/* Push arp module to ip_fd */
if (ioctl (ip_fd, I_POP, NULL) < 0)
syslog (LOG_ERR, "I_POP failed\n");
if (ioctl (ip_fd, I_PUSH, "arp") < 0)
syslog (LOG_ERR, "Can't push ARP module (3)\n");
/* Open arp_fd */
TFR(arp_fd = open ("/dev/tap", O_RDWR, 0));
if (arp_fd < 0)
syslog (LOG_ERR, "Can't open %s\n", "/dev/tap");
/* Set ifname to arp */
strioc_if.ic_cmd = SIOCSLIFNAME;
strioc_if.ic_timout = 0;
strioc_if.ic_len = sizeof(ifr);
strioc_if.ic_dp = (char *)&ifr;
if (ioctl(arp_fd, I_STR, &strioc_if) < 0){
syslog (LOG_ERR, "Can't set ifname to arp\n");
}
if((ip_muxid = ioctl(ip_fd, I_LINK, if_fd)) < 0){
syslog(LOG_ERR, "Can't link TAP device to IP");
return -1;
}
if ((arp_muxid = ioctl (ip_fd, link_type, arp_fd)) < 0)
syslog (LOG_ERR, "Can't link TAP device to ARP");
close (if_fd);
memset(&ifr, 0x0, sizeof(ifr));
pstrcpy(ifr.lifr_name, sizeof(ifr.lifr_name), actual_name);
ifr.lifr_ip_muxid = ip_muxid;
ifr.lifr_arp_muxid = arp_muxid;
if (ioctl (ip_fd, SIOCSLIFMUXID, &ifr) < 0)
{
ioctl (ip_fd, I_PUNLINK , arp_muxid);
ioctl (ip_fd, I_PUNLINK, ip_muxid);
syslog (LOG_ERR, "Can't set multiplexor id");
}
snprintf(dev, dev_size, "tap%d", ppa);
return tap_fd;
}
static int tap_open(char *ifname, int ifname_size,
int *vnet_hdr, int vnet_hdr_required)
{
char dev[10]="";
int fd;
if( (fd = tap_alloc(dev, sizeof(dev))) < 0 ){
fprintf(stderr, "Cannot allocate TAP device\n");
return -1;
}
pstrcpy(ifname, ifname_size, dev);
fcntl(fd, F_SETFL, O_NONBLOCK);
return fd;
}
#elif defined (_AIX)
static int tap_open(char *ifname, int ifname_size,
int *vnet_hdr, int vnet_hdr_required)
{
fprintf (stderr, "no tap on AIX\n");
return -1;
}
#else
static int tap_open(char *ifname, int ifname_size,
int *vnet_hdr, int vnet_hdr_required)
{
struct ifreq ifr;
int fd, ret;
TFR(fd = open("/dev/net/tun", O_RDWR));
if (fd < 0) {
fprintf(stderr, "warning: could not open /dev/net/tun: no virtual network emulation\n");
return -1;
}
memset(&ifr, 0, sizeof(ifr));
ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
if (*vnet_hdr) {
unsigned int features;
if (ioctl(fd, TUNGETFEATURES, &features) == 0 &&
features & IFF_VNET_HDR) {
*vnet_hdr = 1;
ifr.ifr_flags |= IFF_VNET_HDR;
}
if (vnet_hdr_required && !*vnet_hdr) {
qemu_error("vnet_hdr=1 requested, but no kernel "
"support for IFF_VNET_HDR available");
close(fd);
return -1;
}
}
if (ifname[0] != '\0')
pstrcpy(ifr.ifr_name, IFNAMSIZ, ifname);
else
pstrcpy(ifr.ifr_name, IFNAMSIZ, "tap%d");
ret = ioctl(fd, TUNSETIFF, (void *) &ifr);
if (ret != 0) {
fprintf(stderr, "warning: could not configure /dev/net/tun: no virtual network emulation\n");
close(fd);
return -1;
}
pstrcpy(ifname, ifname_size, ifr.ifr_name);
fcntl(fd, F_SETFL, O_NONBLOCK);
return fd;
}
#endif
static int launch_script(const char *setup_script, const char *ifname, int fd)
{
sigset_t oldmask, mask;
int pid, status;
char *args[3];
char **parg;
sigemptyset(&mask);
sigaddset(&mask, SIGCHLD);
sigprocmask(SIG_BLOCK, &mask, &oldmask);
/* try to launch network script */
pid = fork();
if (pid == 0) {
int open_max = sysconf(_SC_OPEN_MAX), i;
for (i = 0; i < open_max; i++) {
if (i != STDIN_FILENO &&
i != STDOUT_FILENO &&
i != STDERR_FILENO &&
i != fd) {
close(i);
}
}
parg = args;
*parg++ = (char *)setup_script;
*parg++ = (char *)ifname;
*parg++ = NULL;
execv(setup_script, args);
_exit(1);
} else if (pid > 0) {
while (waitpid(pid, &status, 0) != pid) {
/* loop */
}
sigprocmask(SIG_SETMASK, &oldmask, NULL);
if (WIFEXITED(status) && WEXITSTATUS(status) == 0) {
return 0;
}
}
fprintf(stderr, "%s: could not launch network script\n", setup_script);
return -1;
}
static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
{
int fd, vnet_hdr_required;
char ifname[128] = {0,};
const char *setup_script;
if (qemu_opt_get(opts, "ifname")) {
pstrcpy(ifname, sizeof(ifname), qemu_opt_get(opts, "ifname"));
}
*vnet_hdr = qemu_opt_get_bool(opts, "vnet_hdr", 1);
if (qemu_opt_get(opts, "vnet_hdr")) {
vnet_hdr_required = *vnet_hdr;
} else {
vnet_hdr_required = 0;
}
TFR(fd = tap_open(ifname, sizeof(ifname), vnet_hdr, vnet_hdr_required));
if (fd < 0) {
return -1;
}
setup_script = qemu_opt_get(opts, "script");
if (setup_script &&
setup_script[0] != '\0' &&
strcmp(setup_script, "no") != 0 &&
launch_script(setup_script, ifname, fd)) {
close(fd);
return -1;
}
qemu_opt_set(opts, "ifname", ifname);
return fd;
}
#endif /* !defined(_WIN32) && !defined(_AIX) */
#if defined(CONFIG_VDE)
typedef struct VDEState {
VLANClientState *vc;
......@@ -2622,7 +2004,7 @@ int qemu_find_nic_model(NICInfo *nd, const char * const *models,
return -1;
}
static int net_handle_fd_param(Monitor *mon, const char *param)
int net_handle_fd_param(Monitor *mon, const char *param)
{
if (!qemu_isdigit(param[0])) {
int fd;
......@@ -2802,78 +2184,6 @@ static int net_init_slirp(QemuOpts *opts,
}
#endif /* CONFIG_SLIRP */
#if !defined(_WIN32) && !defined(_AIX)
int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan)
{
TAPState *s;
int fd, vnet_hdr;
if (qemu_opt_get(opts, "fd")) {
if (qemu_opt_get(opts, "ifname") ||
qemu_opt_get(opts, "script") ||
qemu_opt_get(opts, "downscript") ||
qemu_opt_get(opts, "vnet_hdr")) {
qemu_error("ifname=, script=, downscript= and vnet_hdr= is invalid with fd=\n");
return -1;
}
fd = net_handle_fd_param(mon, qemu_opt_get(opts, "fd"));
if (fd == -1) {
return -1;
}
fcntl(fd, F_SETFL, O_NONBLOCK);
vnet_hdr = tap_probe_vnet_hdr(fd);
} else {
if (!qemu_opt_get(opts, "script")) {
qemu_opt_set(opts, "script", DEFAULT_NETWORK_SCRIPT);
}
if (!qemu_opt_get(opts, "downscript")) {
qemu_opt_set(opts, "downscript", DEFAULT_NETWORK_DOWN_SCRIPT);
}
fd = net_tap_init(opts, &vnet_hdr);
}
s = net_tap_fd_init(vlan, "tap", name, fd, vnet_hdr);
if (!s) {
close(fd);
return -1;
}
if (tap_set_sndbuf(s, opts) < 0) {
return -1;
}
if (qemu_opt_get(opts, "fd")) {
snprintf(s->vc->info_str, sizeof(s->vc->info_str), "fd=%d", fd);
} else {
const char *ifname, *script, *downscript;
ifname = qemu_opt_get(opts, "ifname");
script = qemu_opt_get(opts, "script");
downscript = qemu_opt_get(opts, "downscript");
snprintf(s->vc->info_str, sizeof(s->vc->info_str),
"ifname=%s,script=%s,downscript=%s",
ifname, script, downscript);
if (strcmp(downscript, "no") != 0) {
snprintf(s->down_script, sizeof(s->down_script), "%s", downscript);
snprintf(s->down_script_arg, sizeof(s->down_script_arg), "%s", ifname);
}
}
if (vlan) {
vlan->nb_host_devs++;
}
return 0;
}
#endif /* !defined(_WIN32) && !defined(_AIX) */
static int net_init_socket(QemuOpts *opts,
Monitor *mon,
const char *name,
......
net.h
浏览文件 @ 5281d757
......@@ -174,4 +174,6 @@ void net_host_device_remove(Monitor *mon, const QDict *qdict);
void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd);
int net_handle_fd_param(Monitor *mon, const char *param);
#endif
net/tap.c 0 → 100644
浏览文件 @ 5281d757
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或